X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=arch%2Fx86%2Fkvm%2Fx86.c;h=dd9bc8fb81abddc4dc633dbc20392d1b5fcf14eb;hb=4d7b4ac22fbec1a03206c6cde353f2fd6942f828;hp=aff3479867a8f34bba84e3d83cd44a17bc1cac54;hpb=79fac95ecfa3969aab8119d37ccd7226165f933a;p=safe%2Fjmp%2Flinux-2.6

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index aff3479..dd9bc8f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -39,6 +39,8 @@
 #include <linux/cpufreq.h>
 #include <linux/user-return-notifier.h>
 #include <linux/srcu.h>
+#include <linux/slab.h>
+#include <linux/perf_event.h>
 #include <trace/events/kvm.h>
 #undef TRACE_INCLUDE_FILE
 #define CREATE_TRACE_POINTS
@@ -428,41 +430,38 @@ out:
 
 void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 {
-	if (cr0 & CR0_RESERVED_BITS) {
-		printk(KERN_DEBUG "set_cr0: 0x%lx #GP, reserved bits 0x%lx\n",
-		       cr0, vcpu->arch.cr0);
+	cr0 |= X86_CR0_ET;
+
+#ifdef CONFIG_X86_64
+	if (cr0 & 0xffffffff00000000UL) {
 		kvm_inject_gp(vcpu, 0);
 		return;
 	}
+#endif
+
+	cr0 &= ~CR0_RESERVED_BITS;
 
 	if ((cr0 & X86_CR0_NW) && !(cr0 & X86_CR0_CD)) {
-		printk(KERN_DEBUG "set_cr0: #GP, CD == 0 && NW == 1\n");
 		kvm_inject_gp(vcpu, 0);
 		return;
 	}
 
 	if ((cr0 & X86_CR0_PG) && !(cr0 & X86_CR0_PE)) {
-		printk(KERN_DEBUG "set_cr0: #GP, set PG flag "
-		       "and a clear PE flag\n");
 		kvm_inject_gp(vcpu, 0);
 		return;
 	}
 
 	if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) {
 #ifdef CONFIG_X86_64
-		if ((vcpu->arch.shadow_efer & EFER_LME)) {
+		if ((vcpu->arch.efer & EFER_LME)) {
 			int cs_db, cs_l;
 
 			if (!is_pae(vcpu)) {
-				printk(KERN_DEBUG "set_cr0: #GP, start paging "
-				       "in long mode while PAE is disabled\n");
 				kvm_inject_gp(vcpu, 0);
 				return;
 			}
 			kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
 			if (cs_l) {
-				printk(KERN_DEBUG "set_cr0: #GP, start paging "
-				       "in long mode while CS.L == 1\n");
 				kvm_inject_gp(vcpu, 0);
 				return;
 
@@ -470,8 +469,6 @@ void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 		} else
 #endif
 		if (is_pae(vcpu) && !load_pdptrs(vcpu, vcpu->arch.cr3)) {
-			printk(KERN_DEBUG "set_cr0: #GP, pdptrs "
-			       "reserved bits\n");
 			kvm_inject_gp(vcpu, 0);
 			return;
 		}
@@ -488,7 +485,7 @@ EXPORT_SYMBOL_GPL(kvm_set_cr0);
 
 void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw)
 {
-	kvm_set_cr0(vcpu, (vcpu->arch.cr0 & ~0x0ful) | (msw & 0x0f));
+	kvm_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~0x0ful) | (msw & 0x0f));
 }
 EXPORT_SYMBOL_GPL(kvm_lmsw);
 
@@ -498,28 +495,23 @@ void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE;
 
 	if (cr4 & CR4_RESERVED_BITS) {
-		printk(KERN_DEBUG "set_cr4: #GP, reserved bits\n");
 		kvm_inject_gp(vcpu, 0);
 		return;
 	}
 
 	if (is_long_mode(vcpu)) {
 		if (!(cr4 & X86_CR4_PAE)) {
-			printk(KERN_DEBUG "set_cr4: #GP, clearing PAE while "
-			       "in long mode\n");
 			kvm_inject_gp(vcpu, 0);
 			return;
 		}
 	} else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE)
 		   && ((cr4 ^ old_cr4) & pdptr_bits)
 		   && !load_pdptrs(vcpu, vcpu->arch.cr3)) {
-		printk(KERN_DEBUG "set_cr4: #GP, pdptrs reserved bits\n");
 		kvm_inject_gp(vcpu, 0);
 		return;
 	}
 
 	if (cr4 & X86_CR4_VMXE) {
-		printk(KERN_DEBUG "set_cr4: #GP, setting VMXE\n");
 		kvm_inject_gp(vcpu, 0);
 		return;
 	}
@@ -540,21 +532,16 @@ void kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 
 	if (is_long_mode(vcpu)) {
 		if (cr3 & CR3_L_MODE_RESERVED_BITS) {
-			printk(KERN_DEBUG "set_cr3: #GP, reserved bits\n");
 			kvm_inject_gp(vcpu, 0);
 			return;
 		}
 	} else {
 		if (is_pae(vcpu)) {
 			if (cr3 & CR3_PAE_RESERVED_BITS) {
-				printk(KERN_DEBUG
-				       "set_cr3: #GP, reserved bits\n");
 				kvm_inject_gp(vcpu, 0);
 				return;
 			}
 			if (is_paging(vcpu) && !load_pdptrs(vcpu, cr3)) {
-				printk(KERN_DEBUG "set_cr3: #GP, pdptrs "
-				       "reserved bits\n");
 				kvm_inject_gp(vcpu, 0);
 				return;
 			}
@@ -586,7 +573,6 @@ EXPORT_SYMBOL_GPL(kvm_set_cr3);
 void kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8)
 {
 	if (cr8 & CR8_RESERVED_BITS) {
-		printk(KERN_DEBUG "set_cr8: #GP, reserved bits 0x%lx\n", cr8);
 		kvm_inject_gp(vcpu, 0);
 		return;
 	}
@@ -620,9 +606,11 @@ static inline u32 bit(int bitno)
  * kvm-specific. Those are put in the beginning of the list.
  */
 
-#define KVM_SAVE_MSRS_BEGIN	2
+#define KVM_SAVE_MSRS_BEGIN	5
 static u32 msrs_to_save[] = {
 	MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
+	HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
+	HV_X64_MSR_APIC_ASSIST_PAGE,
 	MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
 	MSR_K6_STAR,
 #ifdef CONFIG_X86_64
@@ -640,15 +628,12 @@ static u32 emulated_msrs[] = {
 static void set_efer(struct kvm_vcpu *vcpu, u64 efer)
 {
 	if (efer & efer_reserved_bits) {
-		printk(KERN_DEBUG "set_efer: 0x%llx #GP, reserved bits\n",
-		       efer);
 		kvm_inject_gp(vcpu, 0);
 		return;
 	}
 
 	if (is_paging(vcpu)
-	    && (vcpu->arch.shadow_efer & EFER_LME) != (efer & EFER_LME)) {
-		printk(KERN_DEBUG "set_efer: #GP, change LME while paging\n");
+	    && (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME)) {
 		kvm_inject_gp(vcpu, 0);
 		return;
 	}
@@ -658,7 +643,6 @@ static void set_efer(struct kvm_vcpu *vcpu, u64 efer)
 
 		feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
 		if (!feat || !(feat->edx & bit(X86_FEATURE_FXSR_OPT))) {
-			printk(KERN_DEBUG "set_efer: #GP, enable FFXSR w/o CPUID capability\n");
 			kvm_inject_gp(vcpu, 0);
 			return;
 		}
@@ -669,7 +653,6 @@ static void set_efer(struct kvm_vcpu *vcpu, u64 efer)
 
 		feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
 		if (!feat || !(feat->ecx & bit(X86_FEATURE_SVM))) {
-			printk(KERN_DEBUG "set_efer: #GP, enable SVM w/o SVM\n");
 			kvm_inject_gp(vcpu, 0);
 			return;
 		}
@@ -678,9 +661,9 @@ static void set_efer(struct kvm_vcpu *vcpu, u64 efer)
 	kvm_x86_ops->set_efer(vcpu, efer);
 
 	efer &= ~EFER_LMA;
-	efer |= vcpu->arch.shadow_efer & EFER_LMA;
+	efer |= vcpu->arch.efer & EFER_LMA;
 
-	vcpu->arch.shadow_efer = efer;
+	vcpu->arch.efer = efer;
 
 	vcpu->arch.mmu.base_role.nxe = (efer & EFER_NX) && !tdp_enabled;
 	kvm_mmu_reset_context(vcpu);
@@ -958,9 +941,13 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		if (msr >= MSR_IA32_MC0_CTL &&
 		    msr < MSR_IA32_MC0_CTL + 4 * bank_num) {
 			u32 offset = msr - MSR_IA32_MC0_CTL;
-			/* only 0 or all 1s can be written to IA32_MCi_CTL */
+			/* only 0 or all 1s can be written to IA32_MCi_CTL
+			 * some Linux kernels though clear bit 10 in bank 4 to
+			 * workaround a BIOS/GART TBL issue on AMD K8s, ignore
+			 * this to avoid an uncatched #GP in the guest
+			 */
 			if ((offset & 0x3) == 0 &&
-			    data != 0 && data != ~(u64)0)
+			    data != 0 && (data | (1 << 10)) != ~(u64)0)
 				return -1;
 			vcpu->arch.mce_banks[offset] = data;
 			break;
@@ -1002,6 +989,100 @@ out:
 	return r;
 }
 
+static bool kvm_hv_hypercall_enabled(struct kvm *kvm)
+{
+	return kvm->arch.hv_hypercall & HV_X64_MSR_HYPERCALL_ENABLE;
+}
+
+static bool kvm_hv_msr_partition_wide(u32 msr)
+{
+	bool r = false;
+	switch (msr) {
+	case HV_X64_MSR_GUEST_OS_ID:
+	case HV_X64_MSR_HYPERCALL:
+		r = true;
+		break;
+	}
+
+	return r;
+}
+
+static int set_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data)
+{
+	struct kvm *kvm = vcpu->kvm;
+
+	switch (msr) {
+	case HV_X64_MSR_GUEST_OS_ID:
+		kvm->arch.hv_guest_os_id = data;
+		/* setting guest os id to zero disables hypercall page */
+		if (!kvm->arch.hv_guest_os_id)
+			kvm->arch.hv_hypercall &= ~HV_X64_MSR_HYPERCALL_ENABLE;
+		break;
+	case HV_X64_MSR_HYPERCALL: {
+		u64 gfn;
+		unsigned long addr;
+		u8 instructions[4];
+
+		/* if guest os id is not set hypercall should remain disabled */
+		if (!kvm->arch.hv_guest_os_id)
+			break;
+		if (!(data & HV_X64_MSR_HYPERCALL_ENABLE)) {
+			kvm->arch.hv_hypercall = data;
+			break;
+		}
+		gfn = data >> HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT;
+		addr = gfn_to_hva(kvm, gfn);
+		if (kvm_is_error_hva(addr))
+			return 1;
+		kvm_x86_ops->patch_hypercall(vcpu, instructions);
+		((unsigned char *)instructions)[3] = 0xc3; /* ret */
+		if (copy_to_user((void __user *)addr, instructions, 4))
+			return 1;
+		kvm->arch.hv_hypercall = data;
+		break;
+	}
+	default:
+		pr_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x "
+			  "data 0x%llx\n", msr, data);
+		return 1;
+	}
+	return 0;
+}
+
+static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data)
+{
+	switch (msr) {
+	case HV_X64_MSR_APIC_ASSIST_PAGE: {
+		unsigned long addr;
+
+		if (!(data & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE)) {
+			vcpu->arch.hv_vapic = data;
+			break;
+		}
+		addr = gfn_to_hva(vcpu->kvm, data >>
+				  HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT);
+		if (kvm_is_error_hva(addr))
+			return 1;
+		if (clear_user((void __user *)addr, PAGE_SIZE))
+			return 1;
+		vcpu->arch.hv_vapic = data;
+		break;
+	}
+	case HV_X64_MSR_EOI:
+		return kvm_hv_vapic_msr_write(vcpu, APIC_EOI, data);
+	case HV_X64_MSR_ICR:
+		return kvm_hv_vapic_msr_write(vcpu, APIC_ICR, data);
+	case HV_X64_MSR_TPR:
+		return kvm_hv_vapic_msr_write(vcpu, APIC_TASKPRI, data);
+	default:
+		pr_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x "
+			  "data 0x%llx\n", msr, data);
+		return 1;
+	}
+
+	return 0;
+}
+
 int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 {
 	switch (msr) {
@@ -1116,6 +1197,16 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		pr_unimpl(vcpu, "unimplemented perfctr wrmsr: "
 			"0x%x data 0x%llx\n", msr, data);
 		break;
+	case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
+		if (kvm_hv_msr_partition_wide(msr)) {
+			int r;
+			mutex_lock(&vcpu->kvm->lock);
+			r = set_msr_hyperv_pw(vcpu, msr, data);
+			mutex_unlock(&vcpu->kvm->lock);
+			return r;
+		} else
+			return set_msr_hyperv(vcpu, msr, data);
+		break;
 	default:
 		if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr))
 			return xen_hvm_config(vcpu, data);
@@ -1215,6 +1306,54 @@ static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	return 0;
 }
 
+static int get_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
+{
+	u64 data = 0;
+	struct kvm *kvm = vcpu->kvm;
+
+	switch (msr) {
+	case HV_X64_MSR_GUEST_OS_ID:
+		data = kvm->arch.hv_guest_os_id;
+		break;
+	case HV_X64_MSR_HYPERCALL:
+		data = kvm->arch.hv_hypercall;
+		break;
+	default:
+		pr_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
+		return 1;
+	}
+
+	*pdata = data;
+	return 0;
+}
+
+static int get_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
+{
+	u64 data = 0;
+
+	switch (msr) {
+	case HV_X64_MSR_VP_INDEX: {
+		int r;
+		struct kvm_vcpu *v;
+		kvm_for_each_vcpu(r, v, vcpu->kvm)
+			if (v == vcpu)
+				data = r;
+		break;
+	}
+	case HV_X64_MSR_EOI:
+		return kvm_hv_vapic_msr_read(vcpu, APIC_EOI, pdata);
+	case HV_X64_MSR_ICR:
+		return kvm_hv_vapic_msr_read(vcpu, APIC_ICR, pdata);
+	case HV_X64_MSR_TPR:
+		return kvm_hv_vapic_msr_read(vcpu, APIC_TASKPRI, pdata);
+	default:
+		pr_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
+		return 1;
+	}
+	*pdata = data;
+	return 0;
+}
+
 int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 {
 	u64 data;
@@ -1266,7 +1405,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 		data |= (((uint64_t)4ULL) << 40);
 		break;
 	case MSR_EFER:
-		data = vcpu->arch.shadow_efer;
+		data = vcpu->arch.efer;
 		break;
 	case MSR_KVM_WALL_CLOCK:
 		data = vcpu->kvm->arch.wall_clock;
@@ -1281,6 +1420,16 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	case MSR_IA32_MCG_STATUS:
 	case MSR_IA32_MC0_CTL ... MSR_IA32_MC0_CTL + 4 * KVM_MAX_MCE_BANKS - 1:
 		return get_msr_mce(vcpu, msr, pdata);
+	case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
+		if (kvm_hv_msr_partition_wide(msr)) {
+			int r;
+			mutex_lock(&vcpu->kvm->lock);
+			r = get_msr_hyperv_pw(vcpu, msr, pdata);
+			mutex_unlock(&vcpu->kvm->lock);
+			return r;
+		} else
+			return get_msr_hyperv(vcpu, msr, pdata);
+		break;
 	default:
 		if (!ignore_msrs) {
 			pr_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr);
@@ -1396,6 +1545,11 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_XEN_HVM:
 	case KVM_CAP_ADJUST_CLOCK:
 	case KVM_CAP_VCPU_EVENTS:
+	case KVM_CAP_HYPERV:
+	case KVM_CAP_HYPERV_VAPIC:
+	case KVM_CAP_HYPERV_SPIN:
+	case KVM_CAP_PCI_SEGMENT:
+	case KVM_CAP_X86_ROBUST_SINGLESTEP:
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:
@@ -1509,8 +1663,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
-	kvm_x86_ops->vcpu_put(vcpu);
 	kvm_put_guest_fpu(vcpu);
+	kvm_x86_ops->vcpu_put(vcpu);
 }
 
 static int is_efer_nx(void)
@@ -1559,6 +1713,7 @@ static int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
 	if (copy_from_user(cpuid_entries, entries,
 			   cpuid->nent * sizeof(struct kvm_cpuid_entry)))
 		goto out_free;
+	vcpu_load(vcpu);
 	for (i = 0; i < cpuid->nent; i++) {
 		vcpu->arch.cpuid_entries[i].function = cpuid_entries[i].function;
 		vcpu->arch.cpuid_entries[i].eax = cpuid_entries[i].eax;
@@ -1576,6 +1731,7 @@ static int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
 	r = 0;
 	kvm_apic_set_version(vcpu);
 	kvm_x86_ops->cpuid_update(vcpu);
+	vcpu_put(vcpu);
 
 out_free:
 	vfree(cpuid_entries);
@@ -1596,9 +1752,11 @@ static int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu,
 	if (copy_from_user(&vcpu->arch.cpuid_entries, entries,
 			   cpuid->nent * sizeof(struct kvm_cpuid_entry2)))
 		goto out;
+	vcpu_load(vcpu);
 	vcpu->arch.cpuid_nent = cpuid->nent;
 	kvm_apic_set_version(vcpu);
 	kvm_x86_ops->cpuid_update(vcpu);
+	vcpu_put(vcpu);
 	return 0;
 
 out:
@@ -1641,10 +1799,12 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 			 u32 index, int *nent, int maxnent)
 {
 	unsigned f_nx = is_efer_nx() ? F(NX) : 0;
-	unsigned f_gbpages = kvm_x86_ops->gb_page_enable() ? F(GBPAGES) : 0;
 #ifdef CONFIG_X86_64
+	unsigned f_gbpages = (kvm_x86_ops->get_lpage_level() == PT_PDPE_LEVEL)
+				? F(GBPAGES) : 0;
 	unsigned f_lm = F(LM);
 #else
+	unsigned f_gbpages = 0;
 	unsigned f_lm = 0;
 #endif
 	unsigned f_rdtscp = kvm_x86_ops->rdtscp_supported() ? F(RDTSCP) : 0;
@@ -2366,18 +2526,18 @@ static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
 	r = 0;
 	switch (chip->chip_id) {
 	case KVM_IRQCHIP_PIC_MASTER:
-		spin_lock(&pic_irqchip(kvm)->lock);
+		raw_spin_lock(&pic_irqchip(kvm)->lock);
 		memcpy(&pic_irqchip(kvm)->pics[0],
 			&chip->chip.pic,
 			sizeof(struct kvm_pic_state));
-		spin_unlock(&pic_irqchip(kvm)->lock);
+		raw_spin_unlock(&pic_irqchip(kvm)->lock);
 		break;
 	case KVM_IRQCHIP_PIC_SLAVE:
-		spin_lock(&pic_irqchip(kvm)->lock);
+		raw_spin_lock(&pic_irqchip(kvm)->lock);
 		memcpy(&pic_irqchip(kvm)->pics[1],
 			&chip->chip.pic,
 			sizeof(struct kvm_pic_state));
-		spin_unlock(&pic_irqchip(kvm)->lock);
+		raw_spin_unlock(&pic_irqchip(kvm)->lock);
 		break;
 	case KVM_IRQCHIP_IOAPIC:
 		r = kvm_set_ioapic(kvm, &chip->chip.ioapic);
@@ -2457,8 +2617,9 @@ static int kvm_vm_ioctl_reinject(struct kvm *kvm,
 int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 				      struct kvm_dirty_log *log)
 {
-	int r, n, i;
+	int r, i;
 	struct kvm_memory_slot *memslot;
+	unsigned long n;
 	unsigned long is_dirty = 0;
 	unsigned long *dirty_bitmap = NULL;
 
@@ -2473,7 +2634,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 	if (!memslot->dirty_bitmap)
 		goto out;
 
-	n = ALIGN(memslot->npages, BITS_PER_LONG) / 8;
+	n = kvm_dirty_bitmap_bytes(memslot);
 
 	r = -ENOMEM;
 	dirty_bitmap = vmalloc(n);
@@ -2595,6 +2756,8 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		if (vpic) {
 			r = kvm_ioapic_init(kvm);
 			if (r) {
+				kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS,
+							  &vpic->dev);
 				kfree(vpic);
 				goto create_irqchip_unlock;
 			}
@@ -2606,10 +2769,8 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = kvm_setup_default_irq_routing(kvm);
 		if (r) {
 			mutex_lock(&kvm->irq_lock);
-			kfree(kvm->arch.vpic);
-			kfree(kvm->arch.vioapic);
-			kvm->arch.vpic = NULL;
-			kvm->arch.vioapic = NULL;
+			kvm_ioapic_destroy(kvm);
+			kvm_destroy_pic(kvm);
 			mutex_unlock(&kvm->irq_lock);
 		}
 	create_irqchip_unlock:
@@ -2863,14 +3024,41 @@ static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v)
 	return kvm_io_bus_read(vcpu->kvm, KVM_MMIO_BUS, addr, len, v);
 }
 
-static int kvm_read_guest_virt(gva_t addr, void *val, unsigned int bytes,
-			       struct kvm_vcpu *vcpu)
+gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, u32 *error)
+{
+	u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
+	return vcpu->arch.mmu.gva_to_gpa(vcpu, gva, access, error);
+}
+
+ gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva, u32 *error)
+{
+	u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
+	access |= PFERR_FETCH_MASK;
+	return vcpu->arch.mmu.gva_to_gpa(vcpu, gva, access, error);
+}
+
+gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, u32 *error)
+{
+	u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
+	access |= PFERR_WRITE_MASK;
+	return vcpu->arch.mmu.gva_to_gpa(vcpu, gva, access, error);
+}
+
+/* uses this to access any guest's mapped memory without checking CPL */
+gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, u32 *error)
+{
+	return vcpu->arch.mmu.gva_to_gpa(vcpu, gva, 0, error);
+}
+
+static int kvm_read_guest_virt_helper(gva_t addr, void *val, unsigned int bytes,
+				      struct kvm_vcpu *vcpu, u32 access,
+				      u32 *error)
 {
 	void *data = val;
 	int r = X86EMUL_CONTINUE;
 
 	while (bytes) {
-		gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr);
+		gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr, access, error);
 		unsigned offset = addr & (PAGE_SIZE-1);
 		unsigned toread = min(bytes, (unsigned)PAGE_SIZE - offset);
 		int ret;
@@ -2893,14 +3081,37 @@ out:
 	return r;
 }
 
+/* used for instruction fetching */
+static int kvm_fetch_guest_virt(gva_t addr, void *val, unsigned int bytes,
+				struct kvm_vcpu *vcpu, u32 *error)
+{
+	u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
+	return kvm_read_guest_virt_helper(addr, val, bytes, vcpu,
+					  access | PFERR_FETCH_MASK, error);
+}
+
+static int kvm_read_guest_virt(gva_t addr, void *val, unsigned int bytes,
+			       struct kvm_vcpu *vcpu, u32 *error)
+{
+	u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
+	return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access,
+					  error);
+}
+
+static int kvm_read_guest_virt_system(gva_t addr, void *val, unsigned int bytes,
+			       struct kvm_vcpu *vcpu, u32 *error)
+{
+	return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, 0, error);
+}
+
 static int kvm_write_guest_virt(gva_t addr, void *val, unsigned int bytes,
-				struct kvm_vcpu *vcpu)
+				struct kvm_vcpu *vcpu, u32 *error)
 {
 	void *data = val;
 	int r = X86EMUL_CONTINUE;
 
 	while (bytes) {
-		gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr);
+		gpa_t gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, error);
 		unsigned offset = addr & (PAGE_SIZE-1);
 		unsigned towrite = min(bytes, (unsigned)PAGE_SIZE - offset);
 		int ret;
@@ -2930,6 +3141,7 @@ static int emulator_read_emulated(unsigned long addr,
 				  struct kvm_vcpu *vcpu)
 {
 	gpa_t                 gpa;
+	u32 error_code;
 
 	if (vcpu->mmio_read_completed) {
 		memcpy(val, vcpu->mmio_data, bytes);
@@ -2939,17 +3151,20 @@ static int emulator_read_emulated(unsigned long addr,
 		return X86EMUL_CONTINUE;
 	}
 
-	gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr);
+	gpa = kvm_mmu_gva_to_gpa_read(vcpu, addr, &error_code);
+
+	if (gpa == UNMAPPED_GVA) {
+		kvm_inject_page_fault(vcpu, addr, error_code);
+		return X86EMUL_PROPAGATE_FAULT;
+	}
 
 	/* For APIC access vmexit */
 	if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE)
 		goto mmio;
 
-	if (kvm_read_guest_virt(addr, val, bytes, vcpu)
+	if (kvm_read_guest_virt(addr, val, bytes, vcpu, NULL)
 				== X86EMUL_CONTINUE)
 		return X86EMUL_CONTINUE;
-	if (gpa == UNMAPPED_GVA)
-		return X86EMUL_PROPAGATE_FAULT;
 
 mmio:
 	/*
@@ -2988,11 +3203,12 @@ static int emulator_write_emulated_onepage(unsigned long addr,
 					   struct kvm_vcpu *vcpu)
 {
 	gpa_t                 gpa;
+	u32 error_code;
 
-	gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr);
+	gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, &error_code);
 
 	if (gpa == UNMAPPED_GVA) {
-		kvm_inject_page_fault(vcpu, addr, 2);
+		kvm_inject_page_fault(vcpu, addr, error_code);
 		return X86EMUL_PROPAGATE_FAULT;
 	}
 
@@ -3056,7 +3272,7 @@ static int emulator_cmpxchg_emulated(unsigned long addr,
 		char *kaddr;
 		u64 val;
 
-		gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr);
+		gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, NULL);
 
 		if (gpa == UNMAPPED_GVA ||
 		   (gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE)
@@ -3093,35 +3309,21 @@ int emulate_invlpg(struct kvm_vcpu *vcpu, gva_t address)
 
 int emulate_clts(struct kvm_vcpu *vcpu)
 {
-	kvm_x86_ops->set_cr0(vcpu, vcpu->arch.cr0 & ~X86_CR0_TS);
+	kvm_x86_ops->set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~X86_CR0_TS));
+	kvm_x86_ops->fpu_activate(vcpu);
 	return X86EMUL_CONTINUE;
 }
 
 int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long *dest)
 {
-	struct kvm_vcpu *vcpu = ctxt->vcpu;
-
-	switch (dr) {
-	case 0 ... 3:
-		*dest = kvm_x86_ops->get_dr(vcpu, dr);
-		return X86EMUL_CONTINUE;
-	default:
-		pr_unimpl(vcpu, "%s: unexpected dr %u\n", __func__, dr);
-		return X86EMUL_UNHANDLEABLE;
-	}
+	return kvm_x86_ops->get_dr(ctxt->vcpu, dr, dest);
 }
 
 int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long value)
 {
 	unsigned long mask = (ctxt->mode == X86EMUL_MODE_PROT64) ? ~0ULL : ~0U;
-	int exception;
 
-	kvm_x86_ops->set_dr(ctxt->vcpu, dr, value & mask, &exception);
-	if (exception) {
-		/* FIXME: better handling */
-		return X86EMUL_UNHANDLEABLE;
-	}
-	return X86EMUL_CONTINUE;
+	return kvm_x86_ops->set_dr(ctxt->vcpu, dr, value & mask);
 }
 
 void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context)
@@ -3135,7 +3337,7 @@ void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context)
 
 	rip_linear = rip + get_segment_base(vcpu, VCPU_SREG_CS);
 
-	kvm_read_guest_virt(rip_linear, (void *)opcodes, 4, vcpu);
+	kvm_read_guest_virt(rip_linear, (void *)opcodes, 4, vcpu, NULL);
 
 	printk(KERN_ERR "emulation failed (%s) rip %lx %02x %02x %02x %02x\n",
 	       context, rip, opcodes[0], opcodes[1], opcodes[2], opcodes[3]);
@@ -3143,7 +3345,8 @@ void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context)
 EXPORT_SYMBOL_GPL(kvm_report_emulation_failure);
 
 static struct x86_emulate_ops emulate_ops = {
-	.read_std            = kvm_read_guest_virt,
+	.read_std            = kvm_read_guest_virt_system,
+	.fetch               = kvm_fetch_guest_virt,
 	.read_emulated       = emulator_read_emulated,
 	.write_emulated      = emulator_write_emulated,
 	.cmpxchg_emulated    = emulator_cmpxchg_emulated,
@@ -3186,8 +3389,9 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
 		vcpu->arch.emulate_ctxt.vcpu = vcpu;
 		vcpu->arch.emulate_ctxt.eflags = kvm_get_rflags(vcpu);
 		vcpu->arch.emulate_ctxt.mode =
+			(!is_protmode(vcpu)) ? X86EMUL_MODE_REAL :
 			(vcpu->arch.emulate_ctxt.eflags & X86_EFLAGS_VM)
-			? X86EMUL_MODE_REAL : cs_l
+			? X86EMUL_MODE_VM86 : cs_l
 			? X86EMUL_MODE_PROT64 :	cs_db
 			? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16;
 
@@ -3279,12 +3483,17 @@ static int pio_copy_data(struct kvm_vcpu *vcpu)
 	gva_t q = vcpu->arch.pio.guest_gva;
 	unsigned bytes;
 	int ret;
+	u32 error_code;
 
 	bytes = vcpu->arch.pio.size * vcpu->arch.pio.cur_count;
 	if (vcpu->arch.pio.in)
-		ret = kvm_write_guest_virt(q, p, bytes, vcpu);
+		ret = kvm_write_guest_virt(q, p, bytes, vcpu, &error_code);
 	else
-		ret = kvm_read_guest_virt(q, p, bytes, vcpu);
+		ret = kvm_read_guest_virt(q, p, bytes, vcpu, &error_code);
+
+	if (ret == X86EMUL_PROPAGATE_FAULT)
+		kvm_inject_page_fault(vcpu, q, error_code);
+
 	return ret;
 }
 
@@ -3305,7 +3514,7 @@ int complete_pio(struct kvm_vcpu *vcpu)
 		if (io->in) {
 			r = pio_copy_data(vcpu);
 			if (r)
-				return r;
+				goto out;
 		}
 
 		delta = 1;
@@ -3332,7 +3541,7 @@ int complete_pio(struct kvm_vcpu *vcpu)
 			kvm_register_write(vcpu, VCPU_REGS_RSI, val);
 		}
 	}
-
+out:
 	io->count -= io->cur_count;
 	io->cur_count = 0;
 
@@ -3375,6 +3584,8 @@ int kvm_emulate_pio(struct kvm_vcpu *vcpu, int in, int size, unsigned port)
 {
 	unsigned long val;
 
+	trace_kvm_pio(!in, port, size, 1);
+
 	vcpu->run->exit_reason = KVM_EXIT_IO;
 	vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT;
 	vcpu->run->io.size = vcpu->arch.pio.size = size;
@@ -3386,11 +3597,10 @@ int kvm_emulate_pio(struct kvm_vcpu *vcpu, int in, int size, unsigned port)
 	vcpu->arch.pio.down = 0;
 	vcpu->arch.pio.rep = 0;
 
-	trace_kvm_pio(vcpu->run->io.direction == KVM_EXIT_IO_OUT, port,
-		      size, 1);
-
-	val = kvm_register_read(vcpu, VCPU_REGS_RAX);
-	memcpy(vcpu->arch.pio_data, &val, 4);
+	if (!vcpu->arch.pio.in) {
+		val = kvm_register_read(vcpu, VCPU_REGS_RAX);
+		memcpy(vcpu->arch.pio_data, &val, 4);
+	}
 
 	if (!kernel_pio(vcpu, vcpu->arch.pio_data)) {
 		complete_pio(vcpu);
@@ -3407,6 +3617,8 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, int in,
 	unsigned now, in_page;
 	int ret = 0;
 
+	trace_kvm_pio(!in, port, size, count);
+
 	vcpu->run->exit_reason = KVM_EXIT_IO;
 	vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT;
 	vcpu->run->io.size = vcpu->arch.pio.size = size;
@@ -3418,9 +3630,6 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, int in,
 	vcpu->arch.pio.down = down;
 	vcpu->arch.pio.rep = rep;
 
-	trace_kvm_pio(vcpu->run->io.direction == KVM_EXIT_IO_OUT, port,
-		      size, count);
-
 	if (!count) {
 		kvm_x86_ops->skip_emulated_instruction(vcpu);
 		return 1;
@@ -3452,10 +3661,8 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, int in,
 	if (!vcpu->arch.pio.in) {
 		/* string PIO write */
 		ret = pio_copy_data(vcpu);
-		if (ret == X86EMUL_PROPAGATE_FAULT) {
-			kvm_inject_gp(vcpu, 0);
+		if (ret == X86EMUL_PROPAGATE_FAULT)
 			return 1;
-		}
 		if (ret == 0 && !pio_string_write(vcpu)) {
 			complete_pio(vcpu);
 			if (vcpu->arch.pio.count == 0)
@@ -3541,6 +3748,51 @@ static void kvm_timer_init(void)
 	}
 }
 
+static DEFINE_PER_CPU(struct kvm_vcpu *, current_vcpu);
+
+static int kvm_is_in_guest(void)
+{
+	return percpu_read(current_vcpu) != NULL;
+}
+
+static int kvm_is_user_mode(void)
+{
+	int user_mode = 3;
+
+	if (percpu_read(current_vcpu))
+		user_mode = kvm_x86_ops->get_cpl(percpu_read(current_vcpu));
+
+	return user_mode != 0;
+}
+
+static unsigned long kvm_get_guest_ip(void)
+{
+	unsigned long ip = 0;
+
+	if (percpu_read(current_vcpu))
+		ip = kvm_rip_read(percpu_read(current_vcpu));
+
+	return ip;
+}
+
+static struct perf_guest_info_callbacks kvm_guest_cbs = {
+	.is_in_guest		= kvm_is_in_guest,
+	.is_user_mode		= kvm_is_user_mode,
+	.get_guest_ip		= kvm_get_guest_ip,
+};
+
+void kvm_before_handle_nmi(struct kvm_vcpu *vcpu)
+{
+	percpu_write(current_vcpu, vcpu);
+}
+EXPORT_SYMBOL_GPL(kvm_before_handle_nmi);
+
+void kvm_after_handle_nmi(struct kvm_vcpu *vcpu)
+{
+	percpu_write(current_vcpu, NULL);
+}
+EXPORT_SYMBOL_GPL(kvm_after_handle_nmi);
+
 int kvm_arch_init(void *opaque)
 {
 	int r;
@@ -3577,6 +3829,8 @@ int kvm_arch_init(void *opaque)
 
 	kvm_timer_init();
 
+	perf_register_guest_info_callbacks(&kvm_guest_cbs);
+
 	return 0;
 
 out:
@@ -3585,6 +3839,8 @@ out:
 
 void kvm_arch_exit(void)
 {
+	perf_unregister_guest_info_callbacks(&kvm_guest_cbs);
+
 	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
 		cpufreq_unregister_notifier(&kvmclock_cpufreq_notifier_block,
 					    CPUFREQ_TRANSITION_NOTIFIER);
@@ -3614,11 +3870,76 @@ static inline gpa_t hc_gpa(struct kvm_vcpu *vcpu, unsigned long a0,
 		return a0 | ((gpa_t)a1 << 32);
 }
 
+int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
+{
+	u64 param, ingpa, outgpa, ret;
+	uint16_t code, rep_idx, rep_cnt, res = HV_STATUS_SUCCESS, rep_done = 0;
+	bool fast, longmode;
+	int cs_db, cs_l;
+
+	/*
+	 * hypercall generates UD from non zero cpl and real mode
+	 * per HYPER-V spec
+	 */
+	if (kvm_x86_ops->get_cpl(vcpu) != 0 || !is_protmode(vcpu)) {
+		kvm_queue_exception(vcpu, UD_VECTOR);
+		return 0;
+	}
+
+	kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
+	longmode = is_long_mode(vcpu) && cs_l == 1;
+
+	if (!longmode) {
+		param = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDX) << 32) |
+			(kvm_register_read(vcpu, VCPU_REGS_RAX) & 0xffffffff);
+		ingpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RBX) << 32) |
+			(kvm_register_read(vcpu, VCPU_REGS_RCX) & 0xffffffff);
+		outgpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDI) << 32) |
+			(kvm_register_read(vcpu, VCPU_REGS_RSI) & 0xffffffff);
+	}
+#ifdef CONFIG_X86_64
+	else {
+		param = kvm_register_read(vcpu, VCPU_REGS_RCX);
+		ingpa = kvm_register_read(vcpu, VCPU_REGS_RDX);
+		outgpa = kvm_register_read(vcpu, VCPU_REGS_R8);
+	}
+#endif
+
+	code = param & 0xffff;
+	fast = (param >> 16) & 0x1;
+	rep_cnt = (param >> 32) & 0xfff;
+	rep_idx = (param >> 48) & 0xfff;
+
+	trace_kvm_hv_hypercall(code, fast, rep_cnt, rep_idx, ingpa, outgpa);
+
+	switch (code) {
+	case HV_X64_HV_NOTIFY_LONG_SPIN_WAIT:
+		kvm_vcpu_on_spin(vcpu);
+		break;
+	default:
+		res = HV_STATUS_INVALID_HYPERCALL_CODE;
+		break;
+	}
+
+	ret = res | (((u64)rep_done & 0xfff) << 32);
+	if (longmode) {
+		kvm_register_write(vcpu, VCPU_REGS_RAX, ret);
+	} else {
+		kvm_register_write(vcpu, VCPU_REGS_RDX, ret >> 32);
+		kvm_register_write(vcpu, VCPU_REGS_RAX, ret & 0xffffffff);
+	}
+
+	return 1;
+}
+
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 {
 	unsigned long nr, a0, a1, a2, a3, ret;
 	int r = 1;
 
+	if (kvm_hv_hypercall_enabled(vcpu->kvm))
+		return kvm_hv_hypercall(vcpu);
+
 	nr = kvm_register_read(vcpu, VCPU_REGS_RAX);
 	a0 = kvm_register_read(vcpu, VCPU_REGS_RBX);
 	a1 = kvm_register_read(vcpu, VCPU_REGS_RCX);
@@ -3661,10 +3982,8 @@ EXPORT_SYMBOL_GPL(kvm_emulate_hypercall);
 int kvm_fix_hypercall(struct kvm_vcpu *vcpu)
 {
 	char instruction[3];
-	int ret = 0;
 	unsigned long rip = kvm_rip_read(vcpu);
 
-
 	/*
 	 * Blow out the MMU to ensure that no other VCPU has an active mapping
 	 * to ensure that the updated hypercall appears atomically across all
@@ -3673,11 +3992,8 @@ int kvm_fix_hypercall(struct kvm_vcpu *vcpu)
 	kvm_mmu_zap_all(vcpu->kvm);
 
 	kvm_x86_ops->patch_hypercall(vcpu, instruction);
-	if (emulator_write_emulated(rip, instruction, 3, vcpu)
-	    != X86EMUL_CONTINUE)
-		ret = -EFAULT;
 
-	return ret;
+	return emulator_write_emulated(rip, instruction, 3, vcpu);
 }
 
 static u64 mk_cr_64(u64 curr_cr, u32 new_val)
@@ -3712,7 +4028,7 @@ unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr)
 
 	switch (cr) {
 	case 0:
-		value = vcpu->arch.cr0;
+		value = kvm_read_cr0(vcpu);
 		break;
 	case 2:
 		value = vcpu->arch.cr2;
@@ -3739,7 +4055,7 @@ void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long val,
 {
 	switch (cr) {
 	case 0:
-		kvm_set_cr0(vcpu, mk_cr_64(vcpu->arch.cr0, val));
+		kvm_set_cr0(vcpu, mk_cr_64(kvm_read_cr0(vcpu), val));
 		*rflags = kvm_get_rflags(vcpu);
 		break;
 	case 2:
@@ -4004,12 +4320,17 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			r = 0;
 			goto out;
 		}
+		if (test_and_clear_bit(KVM_REQ_DEACTIVATE_FPU, &vcpu->requests)) {
+			vcpu->fpu_active = 0;
+			kvm_x86_ops->fpu_deactivate(vcpu);
+		}
 	}
 
 	preempt_disable();
 
 	kvm_x86_ops->prepare_guest_switch(vcpu);
-	kvm_load_guest_fpu(vcpu);
+	if (vcpu->fpu_active)
+		kvm_load_guest_fpu(vcpu);
 
 	local_irq_disable();
 
@@ -4194,7 +4515,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		kvm_set_cr8(vcpu, kvm_run->cr8);
 
 	if (vcpu->arch.pio.cur_count) {
+		vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 		r = complete_pio(vcpu);
+		srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
 		if (r)
 			goto out;
 	}
@@ -4333,12 +4656,12 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 	sregs->gdt.limit = dt.limit;
 	sregs->gdt.base = dt.base;
 
-	sregs->cr0 = vcpu->arch.cr0;
+	sregs->cr0 = kvm_read_cr0(vcpu);
 	sregs->cr2 = vcpu->arch.cr2;
 	sregs->cr3 = vcpu->arch.cr3;
 	sregs->cr4 = kvm_read_cr4(vcpu);
 	sregs->cr8 = kvm_get_cr8(vcpu);
-	sregs->efer = vcpu->arch.shadow_efer;
+	sregs->efer = vcpu->arch.efer;
 	sregs->apic_base = kvm_get_apic_base(vcpu);
 
 	memset(sregs->interrupt_bitmap, 0, sizeof sregs->interrupt_bitmap);
@@ -4426,14 +4749,23 @@ static int load_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
 {
 	struct descriptor_table dtable;
 	u16 index = selector >> 3;
+	int ret;
+	u32 err;
+	gva_t addr;
 
 	get_segment_descriptor_dtable(vcpu, selector, &dtable);
 
 	if (dtable.limit < index * 8 + 7) {
 		kvm_queue_exception_e(vcpu, GP_VECTOR, selector & 0xfffc);
-		return 1;
+		return X86EMUL_PROPAGATE_FAULT;
 	}
-	return kvm_read_guest_virt(dtable.base + index*8, seg_desc, sizeof(*seg_desc), vcpu);
+	addr = dtable.base + index * 8;
+	ret = kvm_read_guest_virt_system(addr, seg_desc, sizeof(*seg_desc),
+					 vcpu,  &err);
+	if (ret == X86EMUL_PROPAGATE_FAULT)
+		kvm_inject_page_fault(vcpu, addr, err);
+
+       return ret;
 }
 
 /* allowed just for 8 bytes segments */
@@ -4447,15 +4779,23 @@ static int save_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
 
 	if (dtable.limit < index * 8 + 7)
 		return 1;
-	return kvm_write_guest_virt(dtable.base + index*8, seg_desc, sizeof(*seg_desc), vcpu);
+	return kvm_write_guest_virt(dtable.base + index*8, seg_desc, sizeof(*seg_desc), vcpu, NULL);
+}
+
+static gpa_t get_tss_base_addr_write(struct kvm_vcpu *vcpu,
+			       struct desc_struct *seg_desc)
+{
+	u32 base_addr = get_desc_base(seg_desc);
+
+	return kvm_mmu_gva_to_gpa_write(vcpu, base_addr, NULL);
 }
 
-static gpa_t get_tss_base_addr(struct kvm_vcpu *vcpu,
+static gpa_t get_tss_base_addr_read(struct kvm_vcpu *vcpu,
 			     struct desc_struct *seg_desc)
 {
 	u32 base_addr = get_desc_base(seg_desc);
 
-	return vcpu->arch.mmu.gva_to_gpa(vcpu, base_addr);
+	return kvm_mmu_gva_to_gpa_read(vcpu, base_addr, NULL);
 }
 
 static u16 get_segment_selector(struct kvm_vcpu *vcpu, int seg)
@@ -4466,18 +4806,6 @@ static u16 get_segment_selector(struct kvm_vcpu *vcpu, int seg)
 	return kvm_seg.selector;
 }
 
-static int load_segment_descriptor_to_kvm_desct(struct kvm_vcpu *vcpu,
-						u16 selector,
-						struct kvm_segment *kvm_seg)
-{
-	struct desc_struct seg_desc;
-
-	if (load_guest_segment_descriptor(vcpu, selector, &seg_desc))
-		return 1;
-	seg_desct_to_kvm_desct(&seg_desc, selector, kvm_seg);
-	return 0;
-}
-
 static int kvm_load_realmode_segment(struct kvm_vcpu *vcpu, u16 selector, int seg)
 {
 	struct kvm_segment segvar = {
@@ -4495,7 +4823,7 @@ static int kvm_load_realmode_segment(struct kvm_vcpu *vcpu, u16 selector, int se
 		.unusable = 0,
 	};
 	kvm_x86_ops->set_segment(vcpu, &segvar, seg);
-	return 0;
+	return X86EMUL_CONTINUE;
 }
 
 static int is_vm86_segment(struct kvm_vcpu *vcpu, int seg)
@@ -4505,35 +4833,112 @@ static int is_vm86_segment(struct kvm_vcpu *vcpu, int seg)
 		(kvm_get_rflags(vcpu) & X86_EFLAGS_VM);
 }
 
-static void kvm_check_segment_descriptor(struct kvm_vcpu *vcpu, int seg,
-					 u16 selector)
-{
-	/* NULL selector is not valid for CS and SS */
-	if (seg == VCPU_SREG_CS || seg == VCPU_SREG_SS)
-		if (!selector)
-			kvm_queue_exception_e(vcpu, TS_VECTOR, selector >> 3);
-}
-
-int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
-				int type_bits, int seg)
+int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, int seg)
 {
 	struct kvm_segment kvm_seg;
+	struct desc_struct seg_desc;
+	u8 dpl, rpl, cpl;
+	unsigned err_vec = GP_VECTOR;
+	u32 err_code = 0;
+	bool null_selector = !(selector & ~0x3); /* 0000-0003 are null */
+	int ret;
 
-	if (is_vm86_segment(vcpu, seg) || !(vcpu->arch.cr0 & X86_CR0_PE))
+	if (is_vm86_segment(vcpu, seg) || !is_protmode(vcpu))
 		return kvm_load_realmode_segment(vcpu, selector, seg);
-	if (load_segment_descriptor_to_kvm_desct(vcpu, selector, &kvm_seg))
-		return 1;
 
-	kvm_check_segment_descriptor(vcpu, seg, selector);
-	kvm_seg.type |= type_bits;
+	/* NULL selector is not valid for TR, CS and SS */
+	if ((seg == VCPU_SREG_CS || seg == VCPU_SREG_SS || seg == VCPU_SREG_TR)
+	    && null_selector)
+		goto exception;
+
+	/* TR should be in GDT only */
+	if (seg == VCPU_SREG_TR && (selector & (1 << 2)))
+		goto exception;
+
+	ret = load_guest_segment_descriptor(vcpu, selector, &seg_desc);
+	if (ret)
+		return ret;
+
+	seg_desct_to_kvm_desct(&seg_desc, selector, &kvm_seg);
+
+	if (null_selector) { /* for NULL selector skip all following checks */
+		kvm_seg.unusable = 1;
+		goto load;
+	}
+
+	err_code = selector & 0xfffc;
+	err_vec = GP_VECTOR;
+
+	/* can't load system descriptor into segment selecor */
+	if (seg <= VCPU_SREG_GS && !kvm_seg.s)
+		goto exception;
+
+	if (!kvm_seg.present) {
+		err_vec = (seg == VCPU_SREG_SS) ? SS_VECTOR : NP_VECTOR;
+		goto exception;
+	}
+
+	rpl = selector & 3;
+	dpl = kvm_seg.dpl;
+	cpl = kvm_x86_ops->get_cpl(vcpu);
 
-	if (seg != VCPU_SREG_SS && seg != VCPU_SREG_CS &&
-	    seg != VCPU_SREG_LDTR)
-		if (!kvm_seg.s)
-			kvm_seg.unusable = 1;
+	switch (seg) {
+	case VCPU_SREG_SS:
+		/*
+		 * segment is not a writable data segment or segment
+		 * selector's RPL != CPL or segment selector's RPL != CPL
+		 */
+		if (rpl != cpl || (kvm_seg.type & 0xa) != 0x2 || dpl != cpl)
+			goto exception;
+		break;
+	case VCPU_SREG_CS:
+		if (!(kvm_seg.type & 8))
+			goto exception;
+
+		if (kvm_seg.type & 4) {
+			/* conforming */
+			if (dpl > cpl)
+				goto exception;
+		} else {
+			/* nonconforming */
+			if (rpl > cpl || dpl != cpl)
+				goto exception;
+		}
+		/* CS(RPL) <- CPL */
+		selector = (selector & 0xfffc) | cpl;
+            break;
+	case VCPU_SREG_TR:
+		if (kvm_seg.s || (kvm_seg.type != 1 && kvm_seg.type != 9))
+			goto exception;
+		break;
+	case VCPU_SREG_LDTR:
+		if (kvm_seg.s || kvm_seg.type != 2)
+			goto exception;
+		break;
+	default: /*  DS, ES, FS, or GS */
+		/*
+		 * segment is not a data or readable code segment or
+		 * ((segment is a data or nonconforming code segment)
+		 * and (both RPL and CPL > DPL))
+		 */
+		if ((kvm_seg.type & 0xa) == 0x8 ||
+		    (((kvm_seg.type & 0xc) != 0xc) && (rpl > dpl && cpl > dpl)))
+			goto exception;
+		break;
+	}
 
+	if (!kvm_seg.unusable && kvm_seg.s) {
+		/* mark segment as accessed */
+		kvm_seg.type |= 1;
+		seg_desc.type |= 1;
+		save_guest_segment_descriptor(vcpu, selector, &seg_desc);
+	}
+load:
 	kvm_set_segment(vcpu, &kvm_seg, seg);
-	return 0;
+	return X86EMUL_CONTINUE;
+exception:
+	kvm_queue_exception_e(vcpu, err_vec, err_code);
+	return X86EMUL_PROPAGATE_FAULT;
 }
 
 static void save_state_to_tss32(struct kvm_vcpu *vcpu,
@@ -4559,6 +4964,14 @@ static void save_state_to_tss32(struct kvm_vcpu *vcpu,
 	tss->ldt_selector = get_segment_selector(vcpu, VCPU_SREG_LDTR);
 }
 
+static void kvm_load_segment_selector(struct kvm_vcpu *vcpu, u16 sel, int seg)
+{
+	struct kvm_segment kvm_seg;
+	kvm_get_segment(vcpu, &kvm_seg, seg);
+	kvm_seg.selector = sel;
+	kvm_set_segment(vcpu, &kvm_seg, seg);
+}
+
 static int load_state_from_tss32(struct kvm_vcpu *vcpu,
 				  struct tss_segment_32 *tss)
 {
@@ -4576,25 +4989,41 @@ static int load_state_from_tss32(struct kvm_vcpu *vcpu,
 	kvm_register_write(vcpu, VCPU_REGS_RSI, tss->esi);
 	kvm_register_write(vcpu, VCPU_REGS_RDI, tss->edi);
 
-	if (kvm_load_segment_descriptor(vcpu, tss->ldt_selector, 0, VCPU_SREG_LDTR))
+	/*
+	 * SDM says that segment selectors are loaded before segment
+	 * descriptors
+	 */
+	kvm_load_segment_selector(vcpu, tss->ldt_selector, VCPU_SREG_LDTR);
+	kvm_load_segment_selector(vcpu, tss->es, VCPU_SREG_ES);
+	kvm_load_segment_selector(vcpu, tss->cs, VCPU_SREG_CS);
+	kvm_load_segment_selector(vcpu, tss->ss, VCPU_SREG_SS);
+	kvm_load_segment_selector(vcpu, tss->ds, VCPU_SREG_DS);
+	kvm_load_segment_selector(vcpu, tss->fs, VCPU_SREG_FS);
+	kvm_load_segment_selector(vcpu, tss->gs, VCPU_SREG_GS);
+
+	/*
+	 * Now load segment descriptors. If fault happenes at this stage
+	 * it is handled in a context of new task
+	 */
+	if (kvm_load_segment_descriptor(vcpu, tss->ldt_selector, VCPU_SREG_LDTR))
 		return 1;
 
-	if (kvm_load_segment_descriptor(vcpu, tss->es, 1, VCPU_SREG_ES))
+	if (kvm_load_segment_descriptor(vcpu, tss->es, VCPU_SREG_ES))
 		return 1;
 
-	if (kvm_load_segment_descriptor(vcpu, tss->cs, 9, VCPU_SREG_CS))
+	if (kvm_load_segment_descriptor(vcpu, tss->cs, VCPU_SREG_CS))
 		return 1;
 
-	if (kvm_load_segment_descriptor(vcpu, tss->ss, 1, VCPU_SREG_SS))
+	if (kvm_load_segment_descriptor(vcpu, tss->ss, VCPU_SREG_SS))
 		return 1;
 
-	if (kvm_load_segment_descriptor(vcpu, tss->ds, 1, VCPU_SREG_DS))
+	if (kvm_load_segment_descriptor(vcpu, tss->ds, VCPU_SREG_DS))
 		return 1;
 
-	if (kvm_load_segment_descriptor(vcpu, tss->fs, 1, VCPU_SREG_FS))
+	if (kvm_load_segment_descriptor(vcpu, tss->fs, VCPU_SREG_FS))
 		return 1;
 
-	if (kvm_load_segment_descriptor(vcpu, tss->gs, 1, VCPU_SREG_GS))
+	if (kvm_load_segment_descriptor(vcpu, tss->gs, VCPU_SREG_GS))
 		return 1;
 	return 0;
 }
@@ -4634,19 +5063,33 @@ static int load_state_from_tss16(struct kvm_vcpu *vcpu,
 	kvm_register_write(vcpu, VCPU_REGS_RSI, tss->si);
 	kvm_register_write(vcpu, VCPU_REGS_RDI, tss->di);
 
-	if (kvm_load_segment_descriptor(vcpu, tss->ldt, 0, VCPU_SREG_LDTR))
+	/*
+	 * SDM says that segment selectors are loaded before segment
+	 * descriptors
+	 */
+	kvm_load_segment_selector(vcpu, tss->ldt, VCPU_SREG_LDTR);
+	kvm_load_segment_selector(vcpu, tss->es, VCPU_SREG_ES);
+	kvm_load_segment_selector(vcpu, tss->cs, VCPU_SREG_CS);
+	kvm_load_segment_selector(vcpu, tss->ss, VCPU_SREG_SS);
+	kvm_load_segment_selector(vcpu, tss->ds, VCPU_SREG_DS);
+
+	/*
+	 * Now load segment descriptors. If fault happenes at this stage
+	 * it is handled in a context of new task
+	 */
+	if (kvm_load_segment_descriptor(vcpu, tss->ldt, VCPU_SREG_LDTR))
 		return 1;
 
-	if (kvm_load_segment_descriptor(vcpu, tss->es, 1, VCPU_SREG_ES))
+	if (kvm_load_segment_descriptor(vcpu, tss->es, VCPU_SREG_ES))
 		return 1;
 
-	if (kvm_load_segment_descriptor(vcpu, tss->cs, 9, VCPU_SREG_CS))
+	if (kvm_load_segment_descriptor(vcpu, tss->cs, VCPU_SREG_CS))
 		return 1;
 
-	if (kvm_load_segment_descriptor(vcpu, tss->ss, 1, VCPU_SREG_SS))
+	if (kvm_load_segment_descriptor(vcpu, tss->ss, VCPU_SREG_SS))
 		return 1;
 
-	if (kvm_load_segment_descriptor(vcpu, tss->ds, 1, VCPU_SREG_DS))
+	if (kvm_load_segment_descriptor(vcpu, tss->ds, VCPU_SREG_DS))
 		return 1;
 	return 0;
 }
@@ -4668,7 +5111,7 @@ static int kvm_task_switch_16(struct kvm_vcpu *vcpu, u16 tss_selector,
 			    sizeof tss_segment_16))
 		goto out;
 
-	if (kvm_read_guest(vcpu->kvm, get_tss_base_addr(vcpu, nseg_desc),
+	if (kvm_read_guest(vcpu->kvm, get_tss_base_addr_read(vcpu, nseg_desc),
 			   &tss_segment_16, sizeof tss_segment_16))
 		goto out;
 
@@ -4676,7 +5119,7 @@ static int kvm_task_switch_16(struct kvm_vcpu *vcpu, u16 tss_selector,
 		tss_segment_16.prev_task_link = old_tss_sel;
 
 		if (kvm_write_guest(vcpu->kvm,
-				    get_tss_base_addr(vcpu, nseg_desc),
+				    get_tss_base_addr_write(vcpu, nseg_desc),
 				    &tss_segment_16.prev_task_link,
 				    sizeof tss_segment_16.prev_task_link))
 			goto out;
@@ -4707,7 +5150,7 @@ static int kvm_task_switch_32(struct kvm_vcpu *vcpu, u16 tss_selector,
 			    sizeof tss_segment_32))
 		goto out;
 
-	if (kvm_read_guest(vcpu->kvm, get_tss_base_addr(vcpu, nseg_desc),
+	if (kvm_read_guest(vcpu->kvm, get_tss_base_addr_read(vcpu, nseg_desc),
 			   &tss_segment_32, sizeof tss_segment_32))
 		goto out;
 
@@ -4715,7 +5158,7 @@ static int kvm_task_switch_32(struct kvm_vcpu *vcpu, u16 tss_selector,
 		tss_segment_32.prev_task_link = old_tss_sel;
 
 		if (kvm_write_guest(vcpu->kvm,
-				    get_tss_base_addr(vcpu, nseg_desc),
+				    get_tss_base_addr_write(vcpu, nseg_desc),
 				    &tss_segment_32.prev_task_link,
 				    sizeof tss_segment_32.prev_task_link))
 			goto out;
@@ -4737,8 +5180,9 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason)
 	int ret = 0;
 	u32 old_tss_base = get_segment_base(vcpu, VCPU_SREG_TR);
 	u16 old_tss_sel = get_segment_selector(vcpu, VCPU_SREG_TR);
+	u32 desc_limit;
 
-	old_tss_base = vcpu->arch.mmu.gva_to_gpa(vcpu, old_tss_base);
+	old_tss_base = kvm_mmu_gva_to_gpa_write(vcpu, old_tss_base, NULL);
 
 	/* FIXME: Handle errors. Failure to read either TSS or their
 	 * descriptors should generate a pagefault.
@@ -4759,7 +5203,10 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason)
 		}
 	}
 
-	if (!nseg_desc.p || get_desc_limit(&nseg_desc) < 0x67) {
+	desc_limit = get_desc_limit(&nseg_desc);
+	if (!nseg_desc.p ||
+	    ((desc_limit < 0x67 && (nseg_desc.type & 8)) ||
+	     desc_limit < 0x2b)) {
 		kvm_queue_exception_e(vcpu, TS_VECTOR, tss_selector & 0xfffc);
 		return 1;
 	}
@@ -4797,7 +5244,7 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason)
 					      &nseg_desc);
 	}
 
-	kvm_x86_ops->set_cr0(vcpu, vcpu->arch.cr0 | X86_CR0_TS);
+	kvm_x86_ops->set_cr0(vcpu, kvm_read_cr0(vcpu) | X86_CR0_TS);
 	seg_desct_to_kvm_desct(&nseg_desc, tss_selector, &tr_seg);
 	tr_seg.type = 11;
 	kvm_set_segment(vcpu, &tr_seg, VCPU_SREG_TR);
@@ -4828,11 +5275,11 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 
 	kvm_set_cr8(vcpu, sregs->cr8);
 
-	mmu_reset_needed |= vcpu->arch.shadow_efer != sregs->efer;
+	mmu_reset_needed |= vcpu->arch.efer != sregs->efer;
 	kvm_x86_ops->set_efer(vcpu, sregs->efer);
 	kvm_set_apic_base(vcpu, sregs->apic_base);
 
-	mmu_reset_needed |= vcpu->arch.cr0 != sregs->cr0;
+	mmu_reset_needed |= kvm_read_cr0(vcpu) != sregs->cr0;
 	kvm_x86_ops->set_cr0(vcpu, sregs->cr0);
 	vcpu->arch.cr0 = sregs->cr0;
 
@@ -4871,7 +5318,7 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	/* Older userspace won't unhalt the vcpu on reset. */
 	if (kvm_vcpu_is_bsp(vcpu) && kvm_rip_read(vcpu) == 0xfff0 &&
 	    sregs->cs.selector == 0xf000 && sregs->cs.base == 0xffff0000 &&
-	    !(vcpu->arch.cr0 & X86_CR0_PE))
+	    !is_protmode(vcpu))
 		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
 
 	vcpu_put(vcpu);
@@ -4973,7 +5420,7 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
 
 	vcpu_load(vcpu);
 	idx = srcu_read_lock(&vcpu->kvm->srcu);
-	gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, vaddr);
+	gpa = kvm_mmu_gva_to_gpa_system(vcpu, vaddr, NULL);
 	srcu_read_unlock(&vcpu->kvm->srcu, idx);
 	tr->physical_address = gpa;
 	tr->valid = gpa != UNMAPPED_GVA;
@@ -5055,14 +5502,14 @@ EXPORT_SYMBOL_GPL(fx_init);
 
 void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 {
-	if (!vcpu->fpu_active || vcpu->guest_fpu_loaded)
+	if (vcpu->guest_fpu_loaded)
 		return;
 
 	vcpu->guest_fpu_loaded = 1;
 	kvm_fx_save(&vcpu->arch.host_fx_image);
 	kvm_fx_restore(&vcpu->arch.guest_fx_image);
+	trace_kvm_fpu(1);
 }
-EXPORT_SYMBOL_GPL(kvm_load_guest_fpu);
 
 void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 {
@@ -5073,8 +5520,9 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 	kvm_fx_save(&vcpu->arch.guest_fx_image);
 	kvm_fx_restore(&vcpu->arch.host_fx_image);
 	++vcpu->stat.fpu_reload;
+	set_bit(KVM_REQ_DEACTIVATE_FPU, &vcpu->requests);
+	trace_kvm_fpu(0);
 }
-EXPORT_SYMBOL_GPL(kvm_put_guest_fpu);
 
 void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 {
@@ -5305,6 +5753,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 		put_page(kvm->arch.apic_access_page);
 	if (kvm->arch.ept_identity_pagetable)
 		put_page(kvm->arch.ept_identity_pagetable);
+	cleanup_srcu_struct(&kvm->srcu);
 	kfree(kvm->arch.aliases);
 	kfree(kvm);
 }